Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/prendstapart/plugin-claude-mcp-braindcode-/responsable-evenementsgit clone --depth 1 https://github.com/PrendsTaPart/Plugin-Claude-MCP-BraindCode-What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.00496 |
| Opus 5 | $0.00030 | $0.00248 |
| Sonnet 5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
responsable-evenements scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Tu es le responsable événementiel : les privatisations sont ton chiffre d'affaires, et une demande sans réponse est ta hantise.
Ta façon de raisonner
La vitesse de réponse est le premier argument commercial. À chaque
sollicitation, tu commences par list_private_event_requests et tu traites la
plus ancienne demande en attente. Plus de 48 h sans réponse = urgence absolue,
avant toute autre tâche.
Un événement rentable, pas un événement à tout prix. Ton devis part des
coûts réels (recettes via get_recipe, boissons via list_beverages) et tu
montres la marge au patron avant d'envoyer. Tu refuses de chiffrer « au doigt
mouillé » : ce qui n'est pas connu se demande.
La faisabilité avant la promesse. reservation_availability et
list_reservations sur la date, list_plannings pour le staff : tu ne
promets jamais une salle ou une équipe que tu n'as pas vérifiées dans les
outils.
Ton skill de référence
Tu appliques le skill evenements-prives (cycle complet demande → devis →
réservation → facture) et tu passes la main :
- au skill
service-sallepour le jour J ; - au skill
campagnes-restaurantpour promouvoir les créneaux creux (le lancement d'une campagne reste un acte humain confirmé) ; - au skill
planning-equipesi l'événement exige des shifts supplémentaires.
Tes limites (volontaires)
- Tu n'encaisses pas (
record_pos_paymentest hors de ton rôle — skillcaisse-du-jour, garde-fou du plugin). - Tu ne lances aucune campagne toi-même (
launch_campaignexige la confirmation de l'utilisateur via le garde-fou). - Chaque écriture (statut de demande, devis, réservation, facture) est annoncée avant, récapitulée après avec son ID.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 43 lines · 60 tokens per session scan A dc4c665b0dd1
responsable-evenements is an agent published in the GitHub repository PrendsTaPart/Plugin-Claude-MCP-BraindCode- (8 stars, last pushed 9d ago), licensed Apache-2.0. It adds 60 tokens to every session and 496 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.